# Task Ambiguity in Humans and Language Models

arXiv: https://arxiv.org/abs/2212.10711 · HTML: https://mlsanity.com/paper/2212.10711/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 51 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [Probabilistic Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.02817/) (2018)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models](https://mlsanity.com/paper/2102.02503/) (2021)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019)
- [Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections](https://mlsanity.com/paper/2104.04670/) (2021)
- [Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations](https://mlsanity.com/paper/2205.12685/) (2022)
- [Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions](https://mlsanity.com/paper/2109.05794/) (2021)

## Built on by (most cited first, 28 of 28)

- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [TheoremQA: A Theorem-driven Question Answering dataset](https://mlsanity.com/paper/2305.12524/) (2023)
- [Understanding Catastrophic Forgetting in Language Models via Implicit Inference](https://mlsanity.com/paper/2309.10105/) (2023)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Eliciting Human Preferences with Language Models](https://mlsanity.com/paper/2310.11589/) (2023)
- [Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations](https://mlsanity.com/paper/2305.13299/) (2023)
- [Can Large Language Models Capture Dissenting Human Voices?](https://mlsanity.com/paper/2305.13788/) (2023)
- [Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity](https://mlsanity.com/paper/2402.06529/) (2024)
- [It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance](https://mlsanity.com/paper/2305.09022/) (2023)
- [Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner](https://mlsanity.com/paper/2406.11978/) (2024)
- [Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answering](https://mlsanity.com/paper/2411.12395/) (2024)
- [Self-Consistency of Large Language Models under Ambiguity](https://mlsanity.com/paper/2310.13439/) (2023)
- [Social Contract AI: Aligning AI Assistants with Implicit Group Norms](https://mlsanity.com/paper/2310.17769/) (2023)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [Lending Interaction Wings to Recommender Systems with Conversational Agents](https://mlsanity.com/paper/2310.04230/) (2023)
- [Towards Unified Alignment Between Agents, Humans, and Environment](https://mlsanity.com/paper/2402.07744/) (2024)
- [Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation](https://mlsanity.com/paper/2510.08044/) (2025)
- [Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?](https://mlsanity.com/paper/2605.07937/) (2026)
- [Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts](https://mlsanity.com/paper/2410.13030/) (2024)
- [ACCORD: Action-Conditioned Contextual Grounding for Language Agents](https://mlsanity.com/paper/2606.16432/) (2026)
- [Expectation Alignment of Language Models for Real-World User Expectations](https://mlsanity.com/paper/2607.20485/) (2026)
- [Where did the ambiguity go? Examining how multimodal models interpret polysemous words](https://mlsanity.com/paper/2608.00410/) (2026)
- [Expert-Guided g-computation with Large Language Models for Estimating Causal Effects on Timings: Applications to Hospital Quality Improvement](https://mlsanity.com/paper/2608.10339/) (2026)
- [A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries](https://mlsanity.com/paper/2608.19875/) (2026)
- [XYEval: Agents say yes to bad advice](https://mlsanity.com/paper/2609.23939/) (2026)

## Abstract (arXiv)

Language models have recently achieved strong performance across a wide range of NLP benchmarks. However, unlike benchmarks, real world tasks are often poorly specified, and agents must deduce the user's intended behavior from a combination of context, instructions, and examples. We investigate how both humans and models behave in the face of such task ambiguity by proposing AmbiBench, a new benchmark of six ambiguously-specified classification tasks. We evaluate humans and models on AmbiBench by seeing how well they identify the intended task using 1) instructions with varying degrees of ambiguity, and 2) different numbers of labeled examples. We find that the combination of model scaling (to 175B parameters) and training with human feedback data enables models to approach or exceed the accuracy of human participants across tasks, but that either one alone is not sufficient. In addition, we show how to dramatically improve the accuracy of language models trained without large-scale human feedback training by finetuning on a small number of ambiguous in-context examples, providing a promising direction for teaching models to generalize well in the face of ambiguity.